Research map / Probabilistic and scientific modeling / Molecules and proteins
Learning Sparse Gaussian Graphical Models with Overlapping Blocks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| allow overlapping blocks (GRAB) versus competing block and sparse methods | GRAB · synthetic chain, tree and lattice blocks | network recovery F1 | Helped |
| GRAB blocks versus k-means, spectral clustering and other methods | GRAB · MILE AML 500 genes, K=10 | number of gene sets revealed (FDR p<0.05) | Helped |
| vary number of blocks K (ablation) | GRAB · MILE AML | gene sets revealed | No clear effect |
| vary kappa in {9,25,49} and overlap o in {.1,.25,.4} (ablation) | GRAB and baselines · synthetic lattice p=400 | network recovery F1 | No clear effect |
| compare genes assigned to 3 or more blocks with known AML driver genes | GRAB · MILE AML | enrichment p-value: p-value: 0.001 | Helped |
| compare learned network of GRAB with GLasso at similar sparsity | GRAB · MILE AML | interpretability of structure | Helped |
Closest papers by meaning
- Learning to Discover Sparse Graphical Models (ICML 2017 · similarity 0.87)
- A Generic Family of Graphical Models: Diversity, Efficiency, and Heterogeneity (ICML 2025 · similarity 0.86)
- Learning Local Neighborhoods of Non-Gaussian Graphical Models (AAAI 2025 · similarity 0.85)
- Sparsest Models Elude Pruning: An Exposé of Pruning’s Current Capabilities (ICML 2024 · similarity 0.84)
- Graph Structure Inference with BAM: Neural Dependency Processing via Bilinear Attention (NeurIPS 2024 · similarity 0.83)
- Inferring Dynamic Networks from Marginals with Iterative Proportional Fitting (ICML 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.